This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
The Combinatorics of Heuristic Search Termination for Object Recognition in Cluttered Environments
September 1991 (vol. 13 no. 9)
pp. 920-935

Many current recognition systems terminate a search once an interpretation that is good enough is found. The author formally examines the combinatorics of this approach, showing that choosing correct termination procedures can dramatically reduce the search. In particular, the author provides conditions on the object model and the scene clutter such that the expected search is at most quartic. The analytic results are shown to be in agreement with empirical data for cluttered object recognition. These results imply that it is critical to use techniques that select subsets of the data likely to have come from a single object before establishing a correspondence between data and model features.

[1] N. Ayache and O. D. Faugeras, "HYPER: A new approach for the recognition and positioning of two-dimensional objects,"IEEE Trans. Patt. Anal. Machine Intell., vol. 8, no. 1, pp. 44-54, 1986.
[2] D. H. Ballard, "Generalizing the Hough transform to detect arbitrary patterns,"Patt. Recogn., vol. 13, no. 2, pp. 111-122, 1981.
[3] R. C. Bolles and R. A. Cain, "Recognizing and locating partially visible objects: The local feature focus method,"Int. J. Robotics Res., vol. 1, no. 3, pp. 57-82, 1982.
[4] M. Drumheller, "Mobile robot localization using sonar,"IEEE Trans. Patt. Anal. Machine Intell., vol. 9, no. 2, pp. 325-332, 1987.
[5] O. D. Faugeras and M. Hebert, "The representation, recognition, and locating of 3-D objects,"Int. J. Robotics Res., vol. 5, no. 3, Fall 1986, pp. 27-52.
[6] E. C. Freuder, "Synthesizing constraint expressions,"Comm. ACM, vol. 21, no. 11, pp. 958-966, 1978.
[7] E. C. Freuder, "A sufficient condition for backtrack-free search,"J. ACM, vol. 29, no. 1, pp. 24-32, 1982.
[8] J. Gaschnig, "Performance measurement and analysis of certain search algorithms," Ph.D. thesis, Carnegie-Mellon Univ., Comput. Sci. Dept., Pittsburgh, PA, 1979.
[9] P. C. Gaston and T. Lozano-Pérez, "Tactile recognition and localization using object models: The case of polyhedra on a plane,"IEEE Trans. Patt. Anal Machine Intell., vol. 6, no. 3, pp. 257-265, 1984.
[10] W. E. L. Grimson, "The combinatorics of object recognition in cluttered environments using constrained search,"Artificial Intell., vol. 44, nos. 1-2, pp. 121-165, 1990.
[11] W. E. L. Grimson, "The effect of indexing on the complexity of object recognition," inProc. Third Int. Conf. Comput. Vision(Osaka, Japan), 1990, pp. 644-651.
[12] W. E. L. Grimson and D. P. Huttenlocher, "On the sensitivity of the Hough transform for object recognition," inProc. Second Int. Conf. Comput. Vision(Tarpon Springs, FL), 1988, pp. 700-706.
[13] W. E. L. Grimson and D. P. Huttenlocher, "On the verification of hypothesized matches in model-based recognition,"IEEE Trans. Patt. Anal. Machine Intell., to be published.
[14] W. E. L. Grimson and T. Lozano-Pérez, "Model-based recognition and localization from sparse range or tactile data,"Int. J. Robotics Res., vol. 3, no. 3, pp. 3-35, 1984.
[15] W. E. L. Grimson and T. Lozano-Perez, "Localizing overlapping parts by searching the interpretation tree,"IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-9, no. 4, July 1987.
[16] R. M. Haralick and G. L. Elliot, "Increasing tree search efficiency for constraint satisfaction problems,"Artificial Intell., vol. 14, pp. 263-313, 1980.
[17] R. M. Haralick and L. G. Shapiro, "The consistent labeling problem: Part 1,"IEEE Trans. Patt. Anal. Machine Intell., vol. 1, no. 4, pp. 173-184, 1979.
[18] D. P. Huttenlocher and S. Ullman, "Object recognition using alignment," inProc. First Int. Conf. Comput. Vision(London), 1987, pp. 102-111.
[19] D. P. Huttenlocher, "Three-dimensional recognition of solid objects from a two-dimensional image," M.I.T. Artificial Intell. Lab., TR 1045, 1989.
[20] D. W. Jacobs, "The use of grouping in visual object recognition," M.I.T. Artificial Intell. Lab., Memo 1023, 1988.
[21] D. Lowe, Perceptual Organization And Visual Recognition. Boston: Kluwer, 1985.
[22] D. G. Lowe, "Three-dimensional object recognition from single two-dimensional images,"Artificial Intell., vol. 31, 1987.
[23] A. K. Mackworth, "Consistency in networks of constraints,"Artificial Intell., vol. 8, pp. 99-118, 1977.
[24] A. K. Mackworth and E. C. Freuder, "The complexity of some polynomial network consistency algorithms for constraint satisfaction problems,"Artificial Intell., vol. 25, pp. 65-74, 1985.
[25] U. Montanari, "Networks of constraints: Fundamental properties and applications to picture processing,"Inform. Sci., vol. 7, pp. 95-132, 1974.
[26] D. W. Murray, "Model-based recognition using 3D structure from motion,"Image Vision Comput., pp. 85-90, 1987.
[27] D. W. Murray, "Model-based recognition using 3D shape alone,"Computer Vision, Graphics and Image Process., vol. 40, pp. 250-266, 1987.
[28] D. W. Murray and D. B. Cook, "Using the orientation of fragmentary 3D edge segments for polyhedral object recognition,"Int. J. Comput. Vision, vol. 2, no. 2, pp. 153-169, 1988.
[29] B. Nudel, "Consistent-labeling problems and their algorithms: Expected-complexities and theory-based heuristics,"Artificial Intell., vol. 21, pp. 135-178, 1983.
[30] A. Sha'ashua and S. Ullman, "Structural saliency: The detection of globally salient structures using a locally connected network," inProc. Second Int. Conf. Comput. Vision(Tarpon Springs, FL), 1988, pp. 321-327.
[31] D. Waltz, "Understanding line drawings of Scenes with shadows," inThe Psychology of Computer Vision(P. Winston, Ed.). New York: McGraw Hill, 1975, pp. 19-91.

Index Terms:
pattern recognition; constrained search model; heuristic search termination; combinatorics; scene clutter; optimisation; pattern recognition; picture processing; search problems
Citation:
W. Eric L. Grimson, "The Combinatorics of Heuristic Search Termination for Object Recognition in Cluttered Environments," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 13, no. 9, pp. 920-935, Sept. 1991, doi:10.1109/34.93810
Usage of this product signifies your acceptance of the Terms of Use.